---
title: "Create inference checkpoint"
method: POST
path: "/rl/training-sessions/{session_id}/operations/inference-checkpoint"
tags: ["RL"]
---

# Create inference checkpoint

`POST /rl/training-sessions/{session_id}/operations/inference-checkpoint`

Submits an operation that will asynchronously save the current LoRA adapter as an inference checkpoint and upload it to object storage.

## Path parameters

- `session_id` string, required — Training session ID

## Response `200`

Inference checkpoint operation details

- RLInferenceCheckpointOperation — Async inference checkpoint operation
  - `id` string, required — Operation ID
  - `status` 'TRAINING_OPERATION_STATUS_UNSPECIFIED' | 'TRAINING_OPERATION_STATUS_PENDING' | 'TRAINING_OPERATION_STATUS_RUNNING' | 'TRAINING_OPERATION_STATUS_COMPLETED' | 'TRAINING_OPERATION_STATUS_FAILED', required
  - `output` RLInferenceCheckpointResult — Result of an inference checkpoint operation
    - `model_name` string, required — Registered model name for downloading the checkpoint
  - `error` RLTrainingOperationError — Error details for a failed training operation
    - `code` 'TRAINING_OPERATION_ERROR_CODE_UNSPECIFIED' | 'TRAINING_OPERATION_ERROR_CODE_RESOURCE_EXHAUSTED' | 'TRAINING_OPERATION_ERROR_CODE_TIMEOUT' | 'TRAINING_OPERATION_ERROR_CODE_INTERNAL_ERROR' | 'TRAINING_OPERATION_ERROR_CODE_SESSION_NOT_ACTIVE' | 'TRAINING_OPERATION_ERROR_CODE_INVALID_INPUT' | 'TRAINING_OPERATION_ERROR_CODE_NON_FINITE_LOSS' — Application error code for a failed training operation
    - `message` string — Human-readable error message

## Other responses

- `default` — An unexpected error response.

---

[API](https://skmtc.net/together/apis/together-apis.md) · [All operations](https://skmtc.net/together/apis/together-apis/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/together/together-apis/revisions/92114e606090/schema)